Bayesian regularization of non-homogeneous dynamic Bayesian networks by globally coupling interaction parameters

Grzegorczyk, M. and Husmeier, D. (2012) Bayesian regularization of non-homogeneous dynamic Bayesian networks by globally coupling interaction parameters. Proceedings of Machine Learning Research, 22, pp. 467-476.

Abstract

To relax the homogeneity assumption of classical dynamic Bayesian networks (DBNs), various recent studies have combined DBNs with multiple changepoint processes. The underlying assumption is that the parameters associated with time series segments delimited by multiple changepoints are a priori independent. Under weak regularity conditions, the parameters can be integrated out in the likelihood, leading to a closed-form expression of the marginal likelihood. However, the assumption of prior independence is unrealistic in many real-world applications, where the segment-specific regulatory relationships among the interdependent quantities tend to undergo gradual evolutionary adaptations. We therefore propose a Bayesian coupling scheme to introduce systematic information sharing among the segment-specific interaction parameters. We investigate the effect this model improvement has on the network reconstruction accuracy in a reverse engineering context, where the objective is to learn the structure of a gene regulatory network from temporal gene expression profiles.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Husmeier, Professor Dirk
• Authors: Grzegorczyk, M., and Husmeier, D.
• College/School: College of Science and Engineering > School of Mathematics and Statistics > Statistics
• Journal Name: Proceedings of Machine Learning Research
• Journal Abbr.: JMLR WCP
• Publisher: PMLR
• ISSN: 1938-7228
• ISSN (Online): 1533-7928
• Copyright Holders: Copyright © 2012 The Authors
• First Published: First published in Proceedings of Machine Learning Research 22: 467-476
• Publisher Policy: Reproduced with the permission of the authors

Related URLs

• Publisher